CN117896671B

CN117896671B - Intelligent management method and system for Bluetooth AOA base station

Info

Publication number: CN117896671B
Application number: CN202410288823.2A
Authority: CN
Inventors: 汪菲; 谢小勇; 管根崇; 贾东升; 张鑫
Original assignee: Jiangsu Lance Electronic Technology Co ltd
Current assignee: Jiangsu Lance Electronic Technology Co ltd
Filing date: 2024-03-14
Publication date: 2024-05-31
Anticipated expiration: 2044-03-14

Abstract

The invention discloses an intelligent management method and system for a Bluetooth AOA base station, wherein the method comprises the following steps: acquiring space map data of a target place, and generating a history aggregation map; if the current day belongs to the hot spot holiday, the active mode and the sleep period of the Bluetooth AOA base station are adjusted according to a preset first base station management strategy, and if the current day belongs to the non-hot spot holiday, the active mode and the sleep period of the Bluetooth AOA base station are adjusted according to the predicted aggregation diagram and a preset second base station management strategy; acquiring a mobile terminal navigation request, and generating an optimal navigation route; and acquiring actual movement data of the mobile terminal, and sequentially activating the base stations of the base station navigation list to complete navigation. The invention effectively integrates data analysis, prediction algorithm and real-time positioning technology, and improves the accuracy and system efficiency of indoor navigation.

Description

Intelligent management method and system for Bluetooth AOA base station

Technical Field

The invention relates to the technical field of indoor positioning, in particular to an intelligent management method and system for a Bluetooth AOA base station.

Background

With the rapid development of mobile communication technology, there is an increasing demand for efficient and accurate indoor positioning and navigation systems. Particularly in large public places such as commercial establishments, shopping centers, airports and the like, the effective navigation system not only can improve user experience, but also can optimize place operation and safety management.

Traditional indoor positioning technologies, such as Wi-Fi, RFID and Bluetooth basic positioning technologies, meet the requirements to a certain extent, but still have the problems of low precision, inflexible management, energy waste, limited user experience and the like.

Disclosure of Invention

In view of this, the embodiment of the invention provides a method and a system for intelligent management of a Bluetooth AOA base station.

In a first aspect, an embodiment of the present invention provides a method for intelligent management of a bluetooth AOA base station, where the method includes:

s1, acquiring space map data of a target place, analyzing historical positioning data of a mobile terminal, dividing a space map into areas, and distributing weight values for each area to generate a historical aggregation map;

S2, judging the class of the current day according to a pre-established hot spot festival set and a non-hot spot festival set, if the current day is judged to belong to the hot spot festival, adjusting the activation mode and the dormancy period of the Bluetooth AOA base station according to a pre-set first base station management strategy, and if the current day is judged to belong to the non-hot spot festival, adjusting the activation mode and the dormancy period of the Bluetooth AOA base station according to a prediction aggregation diagram and a pre-set second base station management strategy;

S3, acquiring a mobile terminal navigation request, and intelligently generating an optimal navigation route according to the space map data of a target place, the navigation destination of the mobile terminal and the layout data of the Bluetooth AOA base station;

s4, acquiring actual movement data of the mobile terminal, generating a base station navigation list according to the current positioning base station and the predicted positioning base station, and sequentially activating the base stations of the base station navigation list to complete navigation.

In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the S1 specifically includes:

Acquiring space map data of a target place by using a high-resolution geospatial scanning technology, using a data optimization technology of a RANSAC algorithm to the space map data so as to remove noise and improve data alignment, and importing the processed data into Autodesk Revit modeling software so as to convert the processed data into a three-dimensional model;

Fusing the building plan and the three-dimensional scanning data by utilizing a point cloud and image fusion algorithm, and correcting, optimizing and adjusting the fused data to generate a final fusion model;

analyzing historical positioning data of the mobile terminal, and identifying a hot spot area in the data by using a K-means clustering algorithm;

calculating the side length L of each cell of the square cell grid, wherein the side length L of each cell is calculated according to the following formula: wherein Q represents a constant, A represents the total area of the target site; n represents the number of historical positioning data, B represents an adjustment coefficient, C represents the average hot spot area, S represents the area of each hot spot area, and M represents the total hot spot area number;

creating the square cell grids on the final fusion model, dividing the space map into areas, and distributing unique identifiers for each cell;

A weight value is assigned to each cell region to generate a history aggregation graph.

The aspects and any possible implementation manner described above further provide an implementation manner, where the modifying and optimizing the adjustment on the fused data specifically includes:

Consistency of the check point cloud data and the building plan in the fused model is achieved, and key features of the two data are compared;

adjusting the point cloud data using a geometry correction tool and algorithm to eliminate the bias;

identifying and repairing any missing or incomplete regions in the fusion model and enhancing using detail enhancement techniques;

Reducing noise in the point cloud data by applying a data smoothing algorithm;

performing structural optimization and data simplification on the fused model;

And finally, verifying and adjusting the fusion model to finish correction, optimization and adjustment of the fused data.

In the aspect and any possible implementation manner described above, there is further provided an implementation manner, where the allocating a weight value to each cell area generates a history aggregation map, and specifically includes:

acquiring historical positioning data of mobile terminals, and mapping the positioning data of each mobile terminal into a corresponding cell area;

And calculating a weight value W of each grid, wherein the weight value W is calculated according to the following formula: wherein/> Representing a cell/>Weight value of/>Expressed in a cell/>Total residence time in/(Representing access cells/>Unique number of users,/>Representing a cell/>Access frequency of/>Respectively representing the maximum residence time, the maximum number of users and the maximum access frequency in all the cells; /(I)、/>、/>Respectively representing weight factors;

Normalizing the weight values of all grids to a 0-1 interval;

Color ranges are defined to represent different aggregation levels, and corresponding colors are given to generate a historical aggregation graph according to the weight value of each grid.

The aspect and any possible implementation manner as described above further provide an implementation manner, where the determining the current day classification according to the pre-established hot spot holiday set and the non-hot spot holiday set specifically includes:

creating two sets using historical data for a preset period of time: a hot spot holiday set and a non-hot spot holiday set;

The method comprises the steps of incorporating the national legal holidays, the double holidays and the holidays with the target place people flow exceeding the set threshold into a hot spot holiday set, and incorporating the holidays with the working days and the target place people flow not exceeding the set threshold into a non-hot spot holiday set;

And when the preset time interval is reached, automatically updating the festival collection.

In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the first base station management policy includes:

If the server judges that the current day belongs to a hot spot holiday, the operation time of the target place is taken as the activation period of all Bluetooth AOA base stations, and the non-operation time is taken as the dormancy period of all Bluetooth AOA base stations;

when the operation time is reached, the state activation of all Bluetooth AOA base stations is completed uniformly;

Monitoring whether a fault Bluetooth AOA base station exists or not, if so, switching a standby base station in the same cell area, and sending a repair request to a maintenance end;

Setting a transition time period before the non-operation time, monitoring positioning data of the mobile terminal when the transition time period is reached, and sending an advanced dormancy instruction to a Bluetooth AOA base station of which the signal range is not covered by a blind area in a target cell area when the positioning data of the cell area is lower than a preset threshold value.

The aspect and any possible implementation manner as described above further provide an implementation manner, where the adjusting the active mode and the sleep period of the bluetooth AOA base station according to the prediction aggregation map and the preset second base station management policy specifically includes:

Activating a Bluetooth AOA base station of the first target aggregation level area at the operation time of the target place according to the first target aggregation level area identified by the historical aggregation graph, and keeping the Bluetooth AOA base station of the first target aggregation level area in a dormant state;

constructing and pre-training a deep learning model, taking a history aggregation graph as an input of the deep learning model, and taking a first prediction aggregation graph as an output;

Activating Bluetooth AOA base stations of the first target aggregation level area and the second target aggregation level area at the operation time of the target place according to the second target aggregation level area identified by the prediction aggregation graph, and keeping the Bluetooth AOA base stations of the first target aggregation level area and the non-second target aggregation level area in a dormant state;

When a preset time interval is reached, updating and generating a history aggregation map, updating a deep learning model, taking the history aggregation map as input of a machine learning model, and taking a second prediction aggregation map as output;

according to the third target aggregation level area identified by the historical aggregation graph, according to the fourth target aggregation level area identified by the second prediction aggregation graph, activating Bluetooth AOA base stations of the third target aggregation level area and the fourth target aggregation level area at the operation time of the target place, and keeping a dormant state by the Bluetooth AOA base stations of the third target aggregation level area and the fourth target aggregation level area;

and when the next preset time interval is reached, repeating the operation until the non-operation time of the target place is reached.

In the aspect and any possible implementation manner as described above, there is further provided an implementation manner, where the S3 specifically includes:

Acquiring a mobile terminal navigation request, and generating an initial navigation path with the shortest distance according to the current position of the mobile terminal in a target place and a destination position;

if the current day belongs to a hot spot holiday, analyzing layout data and a communication range of the Bluetooth AOA base station to calculate the switching times of the base station on an initial navigation path, optimizing the initial navigation path by using an A-type algorithm in a path searching algorithm based on a graph to reduce the switching times of the base station, and generating an optimal navigation route for a mobile terminal to select;

if the current day is judged to belong to a non-hot holiday, a high aggregation level cell area is identified according to a historical aggregation graph, the high aggregation area is marked as an avoiding area, a Dijkstra algorithm in a graph-based path searching algorithm is used for optimizing on the basis of an initial navigation path, and an algorithm setting is adjusted to realize bypassing of the avoiding area in path planning, and an optimal navigation route is generated for a mobile terminal to select according to an algorithm result.

In the foregoing aspect and any possible implementation manner, there is further provided an implementation manner, where the S4 specifically includes:

Collecting position data of the mobile terminal in real time, and periodically updating the position information of the mobile terminal to obtain a movement track;

Constructing and pre-training a circulating neural network model, taking the current position of the mobile terminal, a preset navigation destination and historical track data as inputs, and taking the mobile track of the mobile terminal in a preset time period as output;

Generating a base station navigation list according to a movement track of a preset time period, wherein the base station navigation list comprises all positioning base stations on a path of a mobile terminal and is arranged according to an access sequence of the mobile terminal;

Sequentially activating target base stations on a moving track of a preset time period according to the base station navigation list;

Continuously acquiring real-time position data of the mobile terminal, if the mobile terminal deviates from the moving track of the preset time period, re-predicting the moving track of the preset time period according to the deviation direction, updating a base station navigation list, and adjusting the activated base station until the navigation is completed.

In a second aspect, an embodiment of the present invention provides an intelligent management system for a bluetooth AOA base station, where the system includes:

The map planning module is used for acquiring the space map data of the target place, analyzing the history positioning data of the mobile terminal, dividing the space map into areas, and distributing weight values for each area to generate a history aggregation map;

the management module is used for judging the class of the current day according to a pre-established hot spot holiday set and a non-hot spot holiday set, if the current day is judged to belong to the hot spot holiday, the activation mode and the dormancy period of the Bluetooth AOA base station are adjusted according to a pre-set first base station management strategy, and if the current day is judged to belong to the non-hot spot holiday, the activation mode and the dormancy period of the Bluetooth AOA base station are adjusted according to a prediction aggregation diagram and a pre-set second base station management strategy;

The route generation module is used for acquiring a navigation request of the mobile terminal and intelligently generating an optimal navigation route according to the spatial map data of the quotient, the navigation route of the mobile terminal and the layout data of the Bluetooth AOA base station;

the base station activating module is used for acquiring actual mobile data of the mobile terminal, generating a base station navigation list according to the current positioning base station and the predicted positioning base station, and sequentially activating the base stations of the base station navigation list to complete navigation.

One of the above technical solutions has the following beneficial effects:

The method of the embodiment of the invention provides an intelligent management method and system of a Bluetooth AOA base station, which effectively performs area division and identification of an aggregation area by acquiring and analyzing a space map and historical positioning data; secondly, according to the classification of hot spot holidays and non-hot spot holidays, the activation and dormancy states of the base station are intelligently adjusted, the energy use is optimized, and the service coverage of a high-demand period is ensured; the system can intelligently generate an optimal navigation route according to the real-time space map and the navigation requirement of the user, so that the navigation efficiency is improved; and by utilizing real-time mobile data and a prediction technology, a base station navigation list is dynamically generated, so that the continuity and the precision of the navigation process are ensured, and the user experience is remarkably improved. The method effectively integrates data analysis, prediction algorithm and real-time positioning technology, and improves the accuracy and system efficiency of indoor navigation.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a bluetooth AOA base station intelligent management method S1-S4 according to an embodiment of the present invention;

fig. 2 is a functional block diagram of an intelligent management system for a bluetooth AOA base station according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to specific embodiments and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Please refer to fig. 1, which is a schematic flow chart of a bluetooth AOA base station intelligent management method S1-S4 according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:

According to the invention, through analyzing the historical positioning data and generating the historical aggregation graph, the movement mode and aggregation characteristics of the user in the target place can be more accurately understood, and the method is beneficial to providing more accurate and personalized navigation service for the user; according to the classification of hot spot holidays and non-hot spot holidays, the invention can intelligently adjust the activation and sleep modes of the base station, flexibly switch the management strategy, not only save energy, but also ensure that enough coverage and service are provided in a high-demand period; through automatic and intelligent base station management, the need of manual intervention is reduced, and the maintenance cost and complexity of the system are reduced; according to the space map and the navigation requirements of the user, the method can intelligently generate the optimal navigation route, is particularly useful in a complex indoor environment, and can adjust and optimize the navigation route according to real-time conditions; by utilizing the real-time mobile data and the predicted positioning base station information, the invention can dynamically generate and update the base station navigation list, thereby ensuring that the user always navigates on the optimal path. Therefore, the invention improves the overall efficiency and reliability of the indoor navigation system, is beneficial to better meeting the positioning and navigation requirements of the target places, and can be large-scale commercial or commercial and other large-scale indoor public places.

In a preferred embodiment of the present invention, the S1 specifically includes:

The embodiment of the invention obtains the detailed space information of the target place by using a high-resolution geospatial scanning technology, such as a laser scanning or three-dimensional imaging technology, and provides accurate basic data for subsequent navigation and positioning services; optimizing the space map data by using the RANSAC algorithm, effectively removing noise and improving data alignment, thereby improving the quality and reliability of the data; through a point cloud and image fusion algorithm, a building plan view and three-dimensional scanning data can be effectively combined to generate a fusion model which is more detailed and accurate, and a K-means clustering algorithm is utilized to analyze historical positioning data of a mobile terminal, so that a hot spot area can be identified; by creating square cell grids and distributing unique identifiers to each cell, the effective area division of the space map is realized, so that support is provided for the management and navigation accuracy of the base station; and a weight value is distributed to each cell area, and a history aggregation graph is generated, so that visual visualization of the user activity hot spot is provided, and a decision based on data is realized.

In a preferred embodiment of the present invention, the modifying and optimizing the fused data specifically includes:

Reducing noise in the point cloud data by applying a data smoothing algorithm;

performing structural optimization and data simplification on the fused model;

According to the embodiment of the invention, through the consistency of the check point cloud data and the building plan in the fusion model, the accurate matching among different data sources is ensured, so that the reliability and the accuracy of the whole model are improved; the point cloud data is adjusted by using a geometric correction tool and an algorithm, so that deviation is eliminated, and accurate representation of the space data is ensured; identifying and repairing any missing or incomplete areas in the model, enhancing the details of the model, thereby providing a more comprehensive and detailed spatial representation; the noise in the point cloud data is reduced by applying a data smoothing algorithm, the data quality is obviously improved, and the model is more accurate and clear; the structure optimization and data simplification are carried out on the fused model, so that the processing efficiency and usability of the model are improved, and the model is more suitable for real-time application scenes; and through the final verification and adjustment process, the accuracy and the practicability of the fusion model are ensured.

In a preferred embodiment of the present invention, the step of assigning a weight value to each cell area to generate a history aggregation graph specifically includes:

Acquiring historical positioning data of mobile terminals, and mapping the positioning data of each mobile terminal into a corresponding cell area; and calculating a weight value W of each grid, wherein the weight value W is calculated according to the following formula: wherein/> Representing a cell/>Weight value of/>Expressed in a cell/>Total residence time in/(Representing access cells/>Unique number of users,/>Representing a cell/>Access frequency of/>Respectively representing the maximum residence time, the maximum number of users and the maximum access frequency in all the cells; /(I)、/>、/>Respectively representing weight factors;

Normalizing the weight values of all grids to a 0-1 interval;

According to the embodiment of the invention, the historical positioning data of the mobile terminal is mapped to the cell area, so that the activity intensity of a user in different areas can be accurately represented; calculating and normalizing the weight value of each grid so as to quantize and easily analyze the data; defining color ranges to represent different aggregation levels, and endowing each grid with corresponding colors according to weight values, so that a history aggregation graph is visual and easy to understand, and is helpful for quickly identifying areas with high access frequency; based on analysis of the history aggregation graph, resource allocation, security management and service layout of the target place are optimized; the user experience is enhanced.

In a preferred embodiment of the present invention, the determining the current day classification according to the pre-established hot holiday set and the non-hot holiday set specifically includes:

According to the embodiment of the invention, by effectively distinguishing hot spot holidays from non-hot spot holidays, an accurate basis is provided for intelligent management and operation of a target place, so that the operation efficiency is improved, the user experience is optimized, and the resource allocation and service provision are more targeted and efficient.

In a preferred embodiment of the present invention, the first base station management policy includes:

According to the embodiment of the invention, the activation and dormancy periods of the base station are automatically adjusted according to the operation time of the target place, and the strategy ensures that the base station is in an activation state when needed, so that the energy consumption in a non-operation time period is saved; by monitoring and rapidly responding to the fault base station, timely switching to the standby base station and sending a maintenance request, the stability and the continuity of the base station network are effectively ensured; in a transition time period before the non-operation time, the activation state of the base station is adjusted according to the real-time positioning data, so that the energy utilization efficiency is further improved; the activation mode of the base station is automatically adjusted in the hot spot holiday, so that sufficient service is provided in the period of dense users, and the overall user experience and satisfaction are improved; by accurately controlling the activation period of the base station, particularly, the base station automatically enters the sleep state in a period with less users, so that energy waste is effectively reduced.

In a preferred embodiment of the present invention, the adjusting the active mode and the sleep period of the bluetooth AOA base station according to the predicted aggregation map and the preset second base station management policy specifically includes:

According to the embodiment of the invention, through analysis and prediction of the history aggregation graph, the base station in the specific area can be intelligently activated according to the people flow density in the operation time, so that the strategy ensures effective utilization of resources, and simultaneously meets the requirements of users; the deep learning model is used for predicting the aggregation areas in different time periods, data support is provided for base station activation, and the prediction method improves the accuracy and adaptability of base station management; by maintaining the base station dormant state in non-high aggregate areas, unnecessary energy consumption is significantly reduced while providing adequate coverage when needed; based on the real-time and predicted aggregated data, the strategy can adaptively adjust the operation time of the base station according to the actual situation, so that the flexibility of the system is improved; the history aggregation graph and the deep learning model are updated regularly, so that the base station management strategy is ensured to be always based on the latest data and trend, and the overall response speed and efficiency are improved; providing stable base station service in high user density areas improves user experience and satisfaction, especially during high demand periods.

The method for constructing and pre-training the deep learning model comprises the following steps:

Data collection and preprocessing:

Collecting a sufficient amount of historical aggregate map data, including user location data over different time periods and under various conditions;

Preprocessing the collected data, including cleaning, normalizing and normalizing;

Selecting a deep learning model:

Determining the architecture of the model, such as the number of layers, the number of neurons and the like, by using a convolutional neural network model commonly used in the art;

Characteristic engineering:

Determining input characteristics of a model, and taking a history aggregation graph as input of a deep learning model, wherein the input characteristics comprise regional people flow, time labels and the like in the history aggregation graph;

model training:

Training a deep learning model by using historical aggregate map data, wherein a data set is required to be divided into a training set, a verification set and a test set; during training, model parameters such as learning rate, batch size, etc. are adjusted to optimize performance, and techniques such as cross-validation, early-stop, etc. are applied to prevent overfitting;

Model evaluation and verification:

evaluating performance of the model using the validation set and the test set, the indicators of interest possibly including accuracy, recall, and F1 score; if the performance is poor, returning to the model adjustment step, and adjusting the model structure or carrying out characteristic engineering again;

Model optimization:

Further optimizing the model according to the evaluation result, including adjusting the architecture of the model, increasing or decreasing the data volume, or changing the training strategy;

Deployment and implementation:

Deploying the trained model into an actual application environment for real-time aggregated graph prediction; monitoring real-time performance of the model, and adjusting according to the actual effect;

Continuous iteration and update:

The model is updated and retrained with the newly collected data on a regular basis, ensuring its prediction accuracy and correlation.

It should be noted that, the CNN architecture and parameter selection may be set or adjusted according to actual needs, or may be directly used by selecting the existing technology.

In a preferred embodiment of the present invention, the S3 specifically includes:

According to the embodiment of the invention, the initial navigation path is calculated, and an advanced path searching algorithm, such as an A-based algorithm, is used for optimizing the navigation path in the hot spot holiday, so that the switching times of the base station are reduced, and the navigation consistency and the user experience are improved; in a non-hot holiday, a high-density area is identified according to a history aggregation graph, and a Dijkstra algorithm is used for optimizing a navigation path, so that the high-aggregation area is effectively bypassed, congestion and delay are reduced, and navigation efficiency is improved; acquiring the position and destination information of a mobile terminal in real time, and combining the layout of a base station and historical aggregation data to ensure that the decision of each navigation is based on the latest information; the navigation strategy is adjusted according to the characteristics of different days, so that the optimal navigation experience can be provided for the user under various conditions; the base station switching times of hot spot holidays and the congestion area of non-hot spot holidays are reduced through an intelligent algorithm, the system load is reduced, and the navigation fluency is improved; the safety and reliability of navigation are improved.

In a preferred embodiment of the present invention, the S4 specifically includes:

According to the embodiment of the invention, the movement track of the mobile terminal in the preset time period can be accurately predicted by combining the real-time position data and the historical track data by using the cyclic neural network model; generating a base station navigation list according to the predicted movement track, and activating the base stations in sequence, wherein the design ensures that the base stations are activated only when necessary, thereby improving energy efficiency; the position of the mobile terminal is monitored in real time, if the position deviates from the predicted track, the navigation route is immediately recalculated and adjusted, and the flexibility and the adaptability of the system are improved; unnecessary switching between base stations is reduced by optimizing the navigation path, so that the smoothness of navigation is improved, and delay is reduced; the smoother and more accurate navigation experience is realized, and the user satisfaction is improved; by intelligently managing the activation state of the base station, unnecessary energy consumption is reduced, and long-term operation cost is reduced.

The method for constructing and pre-training the circulating neural network model comprises the following steps:

Data collection and preprocessing:

Collecting a large amount of historical positioning data of the mobile terminal, including the current position, a preset navigation destination and historical track information; removing inaccurate or incomplete data points, and ensuring data quality; all the position data are converted into a unified coordinate system, and normalization processing is carried out, so that the input data are on the same scale;

Characteristic engineering:

Determining model input features including, but not limited to, time stamps, location coordinates, destination coordinates, and the like; converting the temporal and spatial data into a format that can be efficiently processed by the model, such as serializing the temporal data;

Selecting and designing an RNN model:

selecting a network model based on LSTM-RNN, and designing a network structure comprising the number of layers, the number of hidden units and the dimensions of input and output layers;

Training a model:

Dividing the data set into a training set, a verification set and a test set; using a training set training model, adjusting parameters such as learning rate and batch size, and using cross-validation to avoid over-fitting; monitoring the performance of the model on the verification set, and adjusting the parameters and the structure of the model to improve the accuracy;

model evaluation and optimization:

Evaluating the performance of the model on the test set, and using an index of accuracy and recall; model optimization is carried out according to the evaluation result, including network structure adjustment, training data quantity increase or characteristic engineering strategy change;

Deployment and application:

Deploying the trained model into practical application; the model receives position data of the mobile terminal in real time and outputs a predicted movement track; continuously monitoring the performance of the model in actual application, and adjusting according to feedback;

Continuous updating and maintenance:

updating the model periodically using the newly collected data to cope with environmental changes and the evolution of user behavior; the system performance is continuously monitored, and any problems are timely repaired.

It should be noted that, the model RNN architecture and parameter selection may be set or adjusted according to actual needs, or may be directly used by selecting the existing technology.

The embodiment of the invention further provides an embodiment of a device for realizing the steps and the method in the embodiment of the method.

Please refer to fig. 2, which is a functional block diagram of a bluetooth AOA base station intelligent management system according to an embodiment of the present invention, as shown in fig. 2, the bluetooth AOA base station intelligent management system includes:

The map planning module provided by the invention provides an accurate indoor navigation basis for users by analyzing the historical positioning data and the detailed division of the space map, so that the accuracy and the reliability of positioning service are improved; the management module intelligently adjusts the activation and dormancy states of the base station according to the classification of hot spot holidays and non-hot spot holidays, optimizes energy use, and ensures that a user obtains enough service coverage in a high-demand period; the route generation module intelligently generates an optimal navigation route according to the real-time space map data and the user request, so that the navigation efficiency and experience of the user in a complex indoor environment are improved; the base station activation module dynamically generates and updates a base station navigation list by monitoring and predicting the movement track of the user in real time, so that continuity and accuracy in the navigation process are ensured. Therefore, the invention reduces the need of manual intervention and reduces the maintenance cost and complexity of the system through automatic and intelligent base station management; comprehensively considering user behaviors, historical data and real-time environmental changes, the navigation service provided by the system is more personalized and accurate, and the user experience is remarkably improved.

Since each unit module in the present embodiment is capable of executing the method shown in fig. 1, a part of the present embodiment, which is not described in detail, is referred to the related description of fig. 1.

At the hardware level, the apparatus may include a processor, optionally an internal bus, a network interface, a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the device may also include hardware required for other services.

The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc.

And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.

The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above apparatus is described as being functionally divided into various units or modules, respectively. Of course, the functions of each unit or module may be implemented in one or more pieces of software and/or hardware when implementing the invention.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.

Claims

1. An intelligent management method for a Bluetooth AOA base station is characterized by comprising the following steps:

s4, acquiring actual movement data of a mobile terminal, generating a base station navigation list according to a current positioning base station and a predicted positioning base station, and sequentially activating base stations of the base station navigation list to complete navigation;

The first base station management policy includes:

Setting a transition time period before the non-operation time, monitoring positioning data of a mobile terminal when the transition time period is reached, and sending an advanced dormancy instruction to a Bluetooth AOA base station of which the signal range is not covered by a blind area in a target cell area when the positioning data of the cell area is lower than a preset threshold value;

the adjusting the activation mode and the sleep period of the bluetooth AOA base station according to the prediction aggregation diagram and the preset second base station management policy specifically includes:

When the next preset time interval is reached, repeating the operation until reaching the non-operation time of the target place;

The step S3 specifically comprises the following steps:

if the current day is judged to belong to a non-hot holiday, identifying a cell area with a high aggregation level according to a historical aggregation graph, marking the cell area with the high aggregation level as an avoidance area, optimizing on the basis of an initial navigation path by using a Dijkstra algorithm in a graph-based path search algorithm, and adjusting algorithm setting to realize bypassing of the avoidance area in path planning, and generating an optimal navigation route for a mobile terminal to select according to an algorithm result.

2. The method according to claim 1, wherein S1 specifically comprises:

calculating the side length L of each cell of the square cell grid, wherein the side length L of each cell is calculated according to the following formula: wherein, the constant is expressed and the total area of the target place is expressed; the number of historical positioning data, the adjustment coefficient, the average hot spot area, the area of each hot spot area and the total hot spot area number are represented;

3. The method according to claim 2, wherein the modifying and optimizing the fused data specifically comprises:

Reducing noise in the point cloud data by applying a data smoothing algorithm;

performing structural optimization and data simplification on the fused model;

4. The method according to claim 2, wherein the assigning a weight value to each cell area generates a history aggregation map, specifically comprising:

And calculating a weight value W of each grid, wherein the weight value W is calculated according to the following formula: Wherein W _i represents a cell/> Weight value, T _i, is expressed in cell/>Total residence time within N _i represents access cell/>F _i represents the cell/>Is used for the access frequency of (a),Respectively representing the maximum residence time, the maximum number of users and the maximum access frequency in all the cells; /(I)Respectively representing weight factors; normalizing the weight values of all grids to a 0-1 interval;

5. The method according to claim 1, wherein the determining the current day classification according to the pre-established hot spot holiday set and the non-hot spot holiday set specifically comprises:

6. The method according to claim 1, wherein S4 specifically comprises:

7. A Bluetooth AOA base station intelligent management system is characterized by comprising:

The first base station management policy includes:

The route generation module is used for acquiring a navigation request of the mobile terminal and intelligently generating an optimal navigation route according to the spatial map data of the quotient exceeds, the navigation route of the mobile terminal and the layout data of the Bluetooth AOA base station, and specifically comprises the following steps: acquiring a mobile terminal navigation request, and generating an initial navigation path with the shortest distance according to the current position of the mobile terminal in a target place and a destination position; if the current day belongs to a hot spot holiday, analyzing layout data and a communication range of the Bluetooth AOA base station to calculate the switching times of the base station on an initial navigation path, optimizing the initial navigation path by using an A-type algorithm in a path searching algorithm based on a graph to reduce the switching times of the base station, and generating an optimal navigation route for a mobile terminal to select; if the current day is judged to belong to a non-hot holiday, identifying a cell area with a high aggregation level according to a historical aggregation graph, marking the cell area with the high aggregation level as an avoidance area, optimizing on the basis of an initial navigation path by using a Dijkstra algorithm in a graph-based path search algorithm, and adjusting algorithm setting to realize bypassing of the avoidance area in path planning, and generating an optimal navigation route for a mobile terminal to select according to an algorithm result;